Kimi K3.1 Pro tops agentic coding benchmarks but may lag on AA-3D
ArtificialAnlys · x · 2026-10-24
- Artificial Analysis early results: Kimi K3.1 Pro ranks among leading models on agentic knowledge work (GDPval-AA) and coding (Terminal-Bench 4.0).
- However, early signs suggest it will rank lower on AA-3D, their benchmark for building interactive 3D scenes; its predecessor Kimi K3 placed 12th of 22, and K3.1 Pro's Elo is still being voted on.
- Shown example: a 492 m mountain-bike descent with berms, roots, a rock garden and jumps — the demo rides it top to bottom, and users can take over steering, pedaling, and braking at any point.
More from Models
- humans& ships collaborator model Ampersand, social product Boba, and open-sources 10% FTL decode speedup — ericzelikman · 2026-10-24
- Nat Eliason: Blind test 'OVERWHELMINGLY' picks Argon's writing, wants it to rewrite everything — nateliason · 2026-10-24
- GPT-6 Astra solves 49 of 50 research-level physics problems, catches experts' own errors — MoonL88537 · 2026-10-24
- ClaudeAI weekly: silent safety filters, vanishing usage limits, and the Opus 5.5 'nerf' myth — ClaudeAI-mod-bot · 2026-10-24
- Anthropic investigates elevated errors on Claude Fable 5.1 — ClaudeAI-mod-bot · 2026-10-24
- ISTA-DASLab ships GSQ-RCO quantized DeepSeek-V4.1-Flash GGUFs, llama.cpp support still pending — Gold_Coconut9777 · 2026-10-24